© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1656
    Prev
    Next
    INDEX
    Explanations

    for beneficial outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ràng
    2.57
    etí
    2.26
    lemish
    2.20
    赳
    2.15
    туа
    2.12
    pyridazin
    2.10
    ǫ
    2.08
    ේ
    2.05
    licz
    2.02
    媧
    2.02
    POSITIVE LOGITS
     machines
    2.79
    eeee
    2.61
     Machines
    2.50
    床
    2.43
     Machine
    2.43
     Lov
    2.41
     machine
    2.40
    器具
    2.40
    ee
    2.33
     máquinas
    2.32
    Activations Density 0.541%

    No Known Activations